A 540B-parameter LLM improves reasoning performance on GSM8K, DROP, OpenBookQA, and ANLI-A3 by fine-tuning on self-generated high-confidence CoT solutions from unlabeled data.
Jimmy Ba and Rich Caruana
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
SAGE combines SimHash-based stratified sampling with a pluggable gating ensemble of statistical methods to identify confident negatives from unlabeled data, addressing representation bias in positive-unlabeled fraud detection.
citing papers explorer
-
Large Language Models Can Self-Improve
A 540B-parameter LLM improves reasoning performance on GSM8K, DROP, OpenBookQA, and ANLI-A3 by fine-tuning on self-generated high-confidence CoT solutions from unlabeled data.
-
SAGE: Scalable Automatic Gating Ensemble for Confident Negative Harvesting in Fraud Detection
SAGE combines SimHash-based stratified sampling with a pluggable gating ensemble of statistical methods to identify confident negatives from unlabeled data, addressing representation bias in positive-unlabeled fraud detection.